Performance evaluation of tracking for public transport surveillance
Victor C. M. Leung, James Orwell, Sergio A. Velastín · Research Repository (Kingston University London) · 2010
Starting with the end-user requirements, it is argued that the most appropriate performance metric with which to evaluate video-based tracking methods, in the public transport domain, is to measure the information gained through their use.This is equivalent to the reduction in uncertainty about a passenger's whereabouts, after tracking and appearance-based measurements have been taken into account.In this paper, we present a framework for the performance evaluation of such a system.Error propagation analysis is performed to investigate the impact of each system component on the final uncertainty, and allows an end-user requirement to be propagated through the system to determine the minimum performance requirement for each component.This proposed analysis framework is demonstrated on a simulated system.